Upload
others
View
2
Download
0
Embed Size (px)
Citation preview
AdaBoost
Lecturer:Jan Sochman
Authors:Jan Sochman, Jirı Matas
Centre for Machine PerceptionCzech Technical University, Prague
http://cmp.felk.cvut.cz
2/12
Presentation
Outline:
� AdaBoost algorithm
• Why is of interest?
• How it works?
• Why it works?
� AdaBoost variants
3/12
What is AdaBoost?
AdaBoost is an algorithm for constructing a “strong” classifier as linear combination
f(x) =T∑
t=1
αtht(x)
of “simple” “weak” classifiers ht(x).
Terminology
� ht(x) ... “weak” or basis classifier, hypothesis, “feature”
� H(x) = sign(f(x)) ... ‘’strong” or final classifier/hypothesis
Interesting properties
� AB is a linear classifier with all its desirable properties.
� AB output converges to the logarithm of likelihood ratio.
� AB has good generalisation properties.
� AB is a feature selector with a principled strategy (minimisation of upper bound onempirical error).
� AB close to sequential decision making (it produces a sequence of gradually morecomplex classifiers).
4/12
The AdaBoost Algorithm
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}
4/12
The AdaBoost Algorithm
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.
4/12
The AdaBoost Algorithm
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
4/12
The AdaBoost Algorithm
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
t = 1
4/12
The AdaBoost Algorithm
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
t = 1
4/12
The AdaBoost Algorithm
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
t = 1
4/12
The AdaBoost Algorithm
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
t = 1
4/12
The AdaBoost Algorithm
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
Output the final classifier:
H(x) = sign
(T∑
t=1
αtht(x)
)
t = 1
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
4/12
The AdaBoost Algorithm
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
Output the final classifier:
H(x) = sign
(T∑
t=1
αtht(x)
)
t = 2
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
4/12
The AdaBoost Algorithm
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
Output the final classifier:
H(x) = sign
(T∑
t=1
αtht(x)
)
t = 3
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
4/12
The AdaBoost Algorithm
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
Output the final classifier:
H(x) = sign
(T∑
t=1
αtht(x)
)
t = 4
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
4/12
The AdaBoost Algorithm
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
Output the final classifier:
H(x) = sign
(T∑
t=1
αtht(x)
)
t = 5
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
4/12
The AdaBoost Algorithm
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
Output the final classifier:
H(x) = sign
(T∑
t=1
αtht(x)
)
t = 6
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
4/12
The AdaBoost Algorithm
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
Output the final classifier:
H(x) = sign
(T∑
t=1
αtht(x)
)
t = 7
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
4/12
The AdaBoost Algorithm
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
Output the final classifier:
H(x) = sign
(T∑
t=1
αtht(x)
)
t = 40
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
5/12
Reweighting
Effect on the training set
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
exp(−αtyiht(xi)){
< 1, yi = ht(xi)> 1, yi 6= ht(xi)
−2 −1.5 −1 −0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
yf(x)
err
⇒ Increase (decrease) weight of wrongly (correctly) classified examples
⇒ The weight is the upper bound on the error of a given example.
⇒ All information about previously selected “features” is captured in Dt.
5/12
Reweighting
Effect on the training set
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
exp(−αtyiht(xi)){
< 1, yi = ht(xi)> 1, yi 6= ht(xi)
−2 −1.5 −1 −0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
yf(x)
err
⇒ Increase (decrease) weight of wrongly (correctly) classified examples
⇒ The weight is the upper bound on the error of a given example.
⇒ All information about previously selected “features” is captured in Dt.
5/12
Reweighting
Effect on the training set
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
exp(−αtyiht(xi)){
< 1, yi = ht(xi)> 1, yi 6= ht(xi)
−2 −1.5 −1 −0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
yf(x)
err
⇒ Increase (decrease) weight of wrongly (correctly) classified examples
⇒ The weight is the upper bound on the error of a given example.
⇒ All information about previously selected “features” is captured in Dt.
5/12
Reweighting
Effect on the training set
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
exp(−αtyiht(xi)){
< 1, yi = ht(xi)> 1, yi 6= ht(xi)
−2 −1.5 −1 −0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
yf(x)
err
⇒ Increase (decrease) weight of wrongly (correctly) classified examples
⇒ The weight is the upper bound on the error of a given example.
⇒ All information about previously selected “features” is captured in Dt.
6/12
Upper Bound Theorem
Theorem: The following upper bound holds on the training error of H
1m|{i : H(xi) 6= yi}| ≤
T∏t=1
Zt
Proof: By unravelling the update rule
DT+1(i) =exp(−
∑t αtyiht(xi))
m∏
t Zt
=exp(−yif(xi))
m∏
t Zt.
If H(xi) 6= yi then yif(xi) ≤ 0 implying that exp(−yif(xi)) > 1, thus
JH(xi) 6= yiK ≤ exp(−yif(xi))1m
∑i
JH(xi) 6= yiK ≤ 1m
∑i
exp(−yif(xi))
=∑
i
(∏
t
Zt)DT+1(i) =∏
t
Zt−2 −1.5 −1 −0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
yf(x)
err
7/12
Consequences of the Theorem
� Instead of minimising the training error, its upper bound can be minimised.
� This can be done by minimising Zt in each training round by:
• Choosing optimal ht, and
• Finding optimal αt.
� Can be proved to maximise margin.
8/12
Choosing αt
We attempt to minimise Zt =∑
i Dt(i)exp(−αtyiht(xi)):
dZ
dα= −
m∑i=1
D(i)yih(xi)e−yiαih(xi) = 0
−∑
i:yi=h(xi)
D(i)e−α +∑
i:yi 6=h(xi)
D(i)eα = 0
−e−α(1− ε) + eαε = 0
α =12
log1− ε
ε
⇒ The minimisator of the upper bound is αt = 12 log 1−εt
εt.
9/12
Choosing ht
Weak classifier examples
� Decision tree, Perceptron – H infinite
� Selecting the best one from given finite set H
Justification of the weighted error minimisation
Having αt = 12 log 1−εt
εt
Zt =m∑
i=1
Dt(i)e−yiαiht(xi)
=∑
i:yi=ht(xi)
Dt(i)e−αt +∑
i:yi 6=ht(xi)
Dt(i)eαt
= (1− εt)e−αt + εteαt
= 2√
εt(1− εt)
0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 10
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
εt
Z t
⇒ Zt is minimised by selecting ht with minimal weighted error εt.
10/12
The Algorithm Recapitulation
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}
10/12
The Algorithm Recapitulation
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.
10/12
The Algorithm Recapitulation
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
10/12
The Algorithm Recapitulation
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
t = 1
10/12
The Algorithm Recapitulation
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
t = 1
10/12
The Algorithm Recapitulation
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
t = 1
10/12
The Algorithm Recapitulation
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
t = 1
10/12
The Algorithm Recapitulation
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
Output the final classifier:
H(x) = sign
(T∑
t=1
αtht(x)
)
t = 1
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
10/12
The Algorithm Recapitulation
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
Output the final classifier:
H(x) = sign
(T∑
t=1
αtht(x)
)
t = 2
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
10/12
The Algorithm Recapitulation
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
Output the final classifier:
H(x) = sign
(T∑
t=1
αtht(x)
)
t = 3
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
10/12
The Algorithm Recapitulation
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
Output the final classifier:
H(x) = sign
(T∑
t=1
αtht(x)
)
t = 4
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
10/12
The Algorithm Recapitulation
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
Output the final classifier:
H(x) = sign
(T∑
t=1
αtht(x)
)
t = 5
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
10/12
The Algorithm Recapitulation
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
Output the final classifier:
H(x) = sign
(T∑
t=1
αtht(x)
)
t = 6
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
10/12
The Algorithm Recapitulation
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
Output the final classifier:
H(x) = sign
(T∑
t=1
αtht(x)
)
t = 7
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
10/12
The Algorithm Recapitulation
Given: (x1, y1), . . . , (xm, ym);xi ∈ X , yi ∈ {−1,+1}Initialise weights D1(i) = 1/m.For t = 1, ..., T :
� Find ht = arg minhj∈H
εj =m∑
i=1
Dt(i)Jyi 6= hj(xi)K
� If εt ≥ 1/2 then stop
� Set αt = 12 log(1−εt
εt)
� Update
Dt+1(i) =Dt(i)exp(−αtyiht(xi))
Zt
Output the final classifier:
H(x) = sign
(T∑
t=1
αtht(x)
)
t = 40
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
11/12
AdaBoost variants
Freund & Schapire 1995
� Discrete (h : X → {0, 1})
� Multiclass AdaBoost.M1 (h : X → {0, 1, ..., k})
� Multiclass AdaBoost.M2 (h : X → [0, 1]k)
� Real valued AdaBoost.R (Y = [0, 1], h : X → [0, 1])
Schapire & Singer 1997
� Confidence rated prediction (h : X → R, two-class)
� Multilabel AdaBoost.MR, AdaBoost.MH (different formulation of minimised loss)
... Many other modifications since then (WaldBoost, cascaded AB, online AB, ...)
12/12
Pros and cons of AdaBoost
Advantages
� Very simple to implement
� General learning scheme - can be used for various learning tasks
� Feature selection on very large sets of features
� Fairly good generalisation
Disadvantages
� Suboptimal solution (greedy learning)
� Can overfit in presence of noise (has been addressed recently)
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
−2 −1.5 −1 −0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
yf(x)
err
−2 −1.5 −1 −0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
yf(x)
err
−2 −1.5 −1 −0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
yf(x)
err
−2 −1.5 −1 −0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
yf(x)
err
−2 −1.5 −1 −0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
yf(x)
err
−2 −1.5 −1 −0.5 0 0.5 1 1.5 2
0
0.5
1
1.5
2
2.5
3
yf(x)
err
0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 10
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
εt
Z t
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35
0 5 10 15 20 25 30 35 400
0.05
0.1
0.15
0.2
0.25
0.3
0.35